Machine Learning Approaches to Classify Self-Reported Rheumatoid Arthritis Health Scores Using Activity Tracker Data: Longitudinal Observational Study.
Machine Learning Approaches to Classify Self-Reported Rheumatoid Arthritis Health Scores Using Activity Tracker Data: Longitudinal Observational Study.
复制标题
使用活动跟踪器数据来对自我报告的类风湿关节炎健康评分进行分类的机器学习方法：纵向观察研究。
DOI：
10.2196/43107
复制
发表时间：
2023-06-26
影响因子：
2.2
通讯作者：
Arnold, Corey
中科院分区：
文献类型：
--
作者：
Rao, Kaushal;Speier, William;Meng, Yiwen;Wang, Jinhan;Ramesh, Nidhi;Xie, Fenglong;Su, Yujie;Nowell, W. Benjamin;Curtis, Jeffrey R.;Arnold, Corey
关键词：
在移动健康研究中越来越多地使用活动跟踪器来被动收集身体数据，这表明有望减轻参与负担，从而提供积极贡献的患者报告结果 (PRO) 信息。本研究的目的是开发机器学习模型，利用来自类风湿性关节炎患者队列的 Fitbit 数据对 PRO 分数进行分类和预测。建立了两种不同的模型来对 PRO 分数进行分类：一个是随机森林分类器模型，在对 PRO 分数进行每周预测时独立处理每周的观察结果；另一个是隐马尔可夫模型，该模型还考虑了连续几周之间的相关性。分析比较模型评估指标：(1) 区分正常 PRO 分数和严重 PRO 分数的二元任务；以及 (2) 对给定周的 PRO 分数状态进行分类的多类任务。对于二元和多类任务，隐马尔可夫模型在所有 PRO 分数上均显着（P<.05）优于随机森林模型，最高曲线下面积、Pearson 相关系数和 Cohen κ 系数分别为 0.750、0.479 和 0.471。虽然我们的结果和在现实环境中的评估仍有待进一步验证，但这项研究证明了身体活动跟踪器数据能够对类风湿关节炎患者随时间的健康状况进行分类，并使得根据需要安排预防性临床干预成为可能。如果可以实时监测患者的治疗结果，就有可能改善其他慢性病患者的临床护理。
The increasing use of activity trackers in mobile health studies to passively collect physical data has shown promise in lessening participation burden to provide actively contributed patient-reported outcome (PRO) information. The aim of this study was to develop machine learning models to classify and predict PRO scores using Fitbit data from a cohort of patients with rheumatoid arthritis. Two different models were built to classify PRO scores: a random forest classifier model that treated each week of observations independently when making weekly predictions of PRO scores, and a hidden Markov model that additionally took correlations between successive weeks into account. Analyses compared model evaluation metrics for (1) a binary task of distinguishing a normal PRO score from a severe PRO score and (2) a multiclass task of classifying a PRO score state for a given week. For both the binary and multiclass tasks, the hidden Markov model significantly (P<.05) outperformed the random forest model for all PRO scores, and the highest area under the curve, Pearson correlation coefficient, and Cohen κ coefficient were 0.750, 0.479, and 0.471, respectively. While further validation of our results and evaluation in a real-world setting remains, this study demonstrates the ability of physical activity tracker data to classify health status over time in patients with rheumatoid arthritis and enables the possibility of scheduling preventive clinical interventions as needed. If patient outcomes can be monitored in real time, there is potential to improve clinical care for patients with other chronic conditions.
登录
查看更多内容
影响因子：
4
作者：
Azevedo, Rita;Bernardes, Miguel;Lima, Aurea
通讯作者：
Lima, Aurea
影响因子：
5
作者：
Hermsen, Sander;Moons, Jonas;De Groot, Martijn
通讯作者：
De Groot, Martijn
影响因子：
15.2
作者：
Rajkomar, Alvin;Oren, Eyal;Dean, Jeffrey
通讯作者：
Dean, Jeffrey
影响因子：
1.7
作者：
Nowell, William Benjamin;Curtis, Jeffrey R.;Haynes, Virginia S.
通讯作者：
Haynes, Virginia S.
影响因子：
5
作者：
Reade S;Spencer K;Sergeant JC;Sperrin M;Schultz DM;Ainsworth J;Lakshminarayana R;Hellman B;James B;McBeth J;Sanders C;Dixon WG
通讯作者：
Dixon WG